A Within-Person Randomized Controlled Pilot Study to Evaluate the Ability of a Point-of-Care Artificial Intelligence-Enabled Multispectral Imaging Device to Manage Leg Ulcers in Leprosy.

Abstract

Objective: To evaluate the clinical utility of a point-of-care, artificial intelligence-enabled multispectral imaging device in guiding targeted debridement of chronic leg ulcers in patients with leprosy, using a within-person randomized controlled pilot design.

Methods: Five adult male patients with lepromatous leprosy and at least 2 chronic leg ulcers each were enrolled in a split-body design. One ulcer per patient was randomized to the experimental arm (EA), where weekly debridement was guided by multispectral imaging, and the other to the control arm (CA), which received standard care. The device used autofluorescence to identify areas of suspected bacterial colonization and provided Gram-type classification. Healing was assessed by changes in wound area and Pressure Ulcer Scale for Healing scores over 18 weeks. Microbial confirmation was performed using standardized swab cultures.

Results: At 18 weeks, the mean wound size reduction was greater in the EA (84.46%) than in the CA (73.28%). Pressure Ulcer Scale for Healing scores decreased more rapidly in the EA (from 11.4 to 4.75) compared with the CA (from 11.0 to 6.75). One ulcer in each arm achieved full epithelialization, but the EA ulcer healed faster (5 vs. 9 weeks). Autofluorescence imaging enabled targeted systemic antimicrobial use in several cases. No adverse events were reported.

Conclusions: This pilot, the first of its kind in leprosy ulcer care, demonstrates the potential of artificial intelligence-enabled multispectral imaging to enhance wound healing through guided debridement. The technology offers real-time, noninvasive infection assessment that may support more effective, individualized wound management. Larger, blinded studies are warranted to validate these findings.